Instructions to use philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX"

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX

Run Hermes

hermes

MLX LM

How to use philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "philipjohnbasile/GLM-5.2-Demolition-q4a4-soul-MLX",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

philipjohnbasile commited on 14 days ago

Commit

99d5478

verified ·

1 Parent(s): 9f85410

Upload design/facet_calib.py with huggingface_hub

Browse files

Files changed (1) hide show

design/facet_calib.py +7 -0

design/facet_calib.py CHANGED Viewed

@@ -13,6 +13,7 @@ import glob
 import json
 import os
 import random
 from collections import Counter
 HERE = os.path.dirname(__file__)
@@ -43,6 +44,12 @@ def main():
         mix.append((os.path.basename(fp).split("_")[0], open(fp, encoding="utf-8", errors="ignore").read()))
     for t in _sample("heal/design/seeds.jsonl", 9):
         mix.append(("design", t))
     # 2) balanced samples per capability from the heal corpora
     for cap, rel, k in [("design", "heal/design/train.jsonl", 40),
                         ("math", "heal/lean/train.jsonl", 40),

 import json
 import os
 import random
+import sys
 from collections import Counter
 HERE = os.path.dirname(__file__)
         mix.append((os.path.basename(fp).split("_")[0], open(fp, encoding="utf-8", errors="ignore").read()))
     for t in _sample("heal/design/seeds.jsonl", 9):
         mix.append(("design", t))
+    # the facet CANONS — dense facet vocabulary (OKLCH/Tufte/Saltzer/Erdős/…), a strong per-facet REAP activator
+    # that exercises each facet's experts so a harder prune (14/7GB) keeps them. Full balance comes from the flywheel.
+    sys.path.insert(0, os.path.join(ROOT, "src"))
+    from soul import FACETS  # noqa: E402
+    for name, facet in FACETS.items():
+        mix.append((name, facet.canon))
     # 2) balanced samples per capability from the heal corpora
     for cap, rel, k in [("design", "heal/design/train.jsonl", 40),
                         ("math", "heal/lean/train.jsonl", 40),